Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases used to contrast or connect ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unei
    -0.16
    lek
    -0.16
    /Gate
    -0.15
    roti
    -0.15
    issional
    -0.15
    illos
    -0.15
     лак
    -0.15
    cname
    -0.14
    "",↵
    -0.13
    onces
    -0.13
    POSITIVE LOGITS
    sport
    0.16
    aran
    0.15
    å¤
    0.15
    _cpp
    0.15
    lamaz
    0.15
    isto
    0.15
    yl
    0.14
    .Api
    0.14
    158
    0.14
    zen
    0.14
    Act Density 0.165%

    No Known Activations